DeepNeuro: an open-source deep learning toolbox for neuroimaging

TL;DR

DeepNeuro is an open-source framework that simplifies designing, training, and deploying deep learning models for neuroimaging, ensuring consistency and ease of use across different clinical settings.

Contribution

It introduces a flexible, user-friendly toolkit for neuroimaging deep learning, including preprocessing, architecture modification, and deployment via Docker containers.

Findings

Supports design and training of neural networks for neuroimaging.

Provides preprocessing and postprocessing functions for consistent results.

Enables packaging pipelines into Docker containers for sharing and deployment.

Abstract

Translating neural networks from theory to clinical practice has unique challenges, specifically in the field of neuroimaging. In this paper, we present DeepNeuro, a deep learning framework that is best-suited to putting deep learning algorithms for neuroimaging in practical usage with a minimum of friction. We show how this framework can be used to both design and train neural network architectures, as well as modify state-of-the-art architectures in a flexible and intuitive way. We display the pre- and postprocessing functions common in the medical imaging community that DeepNeuro offers to ensure consistent performance of networks across variable users, institutions, and scanners. And we show how pipelines created in DeepNeuro can be concisely packaged into shareable Docker containers and command-line interfaces using DeepNeuro's pipeline resources.